Skills Management in Unique AI Conduct

Overview

Skills are reusable capability packages that extend the Conduct agent's behavior for specific workflows.

Skills reach a session from three independent places:

• Knowledge Base skills are authored by your organization and stored as folders in the Knowledge Base. A Conduct space with the Skills tool loads the company and team skills in the root folder selected on that tool, plus company and team skills from any additional folders you attach. If no root folder is selected, the space runs on built-in skills only.

• Personal skills are saved by each user in their own home folder, under <HOME>/skills-conduct/space-<spaceId>/. Only that user can open the folder, and only the space it is named after loads it.

• Built-in skills ship with the product. These are not stored in the Knowledge Base.

This article covers how to organize, manage, and create skills for your organization.

Who is it for?

Administrators responsible for configuring Conduct spaces and managing the skills library for their organization.

If you're unable to access the features discussed on this page, it's possible that your company does not have access or hasn't upgraded to the latest version yet. Please reach out to your internal support team or Unique's customer success team for assistance.

Permissions and Ownership

Managing skills involves two separate permissions:

• Manage access on the space — to enable the Skills tool and choose which Knowledge Base folder it loads. Held by the space owner, space managers, and company-wide space administrators.

• Write access on a Knowledge Base folder — to add or edit the skills inside it. This is what skill authors need, and it is granted per folder.

The two are independent: managing a space does not let you edit the skills it loads, and having write access to a skills folder does not let you point a space at it. Saving a personal skill does not require either permission. It requires Personal skills creation to be on for the space. The skill is written to that user's home folder, under <HOME>/skills-conduct/space-<spaceId>/. That folder is created on the first save and does not inherit access from any other folder. If the user has no home folder, the save stops. Turning Personal skills creation off stops new saves. Skills that user already saved stay loaded in that space.

We recommend assigning ownership per folder — company-wide folders to a small group of skills admins, team folders to team leads. These are organizational roles, implemented purely by granting Knowledge Base write access on the matching folders.

Skill Anatomy

Every skill is a folder containing at minimum a SKILL.md file:

my-skill/
├── SKILL.md           ← Required — manifest with instructions
├── scripts/           ← Optional — executable code for deterministic tasks
├── references/        ← Optional — docs loaded into context as needed
├── assets/            ← Optional — templates, icons, fonts
└── examples/          ← Optional — input/output examples

Any folder anywhere under the space's skills folder that contains a SKILL.md is treated as a skill, and its entire subtree is loaded with it. Grouping folders are therefore free to nest as deeply as you like.

SKILL.md Format

---
name: "financial-document-parser"
description: "Extracts key data points, tables, and metadata from financial documents (10-K, DDQ, side letters). Use when the user uploads a financial PDF or asks to parse/extract from a regulatory document."
---

[Detailed instructions for the agent — what to extract, how to format output,
edge cases to handle, quality checks to run]

The name and description in the front matter are critical — the description determines when the agent selects this skill. Make it specific about trigger conditions.

For a comprehensive guide on skill authoring — including best practices, structure patterns, and examples — visit agentskills.io.

Organizing Skills

Skills that your organization creates are stored in the Knowledge Base. A Conduct space loads them from the root folder selected on the Skills tool (skills-conduct by default) and, when you add them, from further folders. Name prefixes on the immediate children of a skills folder set the layer: team- folders are the team layer, and company-, space-, and unprefixed folders are the company layer. Use the prefixes to match how ownership works in your organization. Personal skills never live under a skills folder. Below is an example of a folder structure:

skills-conduct/                      ← root folder selected on the space
├── company-core/                    company layer
│   ├── house-style-memo/
│   └── compliance-disclaimer-injector/
├── team-credit/                     team layer
└── use-cases/                       company layer, no prefix
    └── ddq-rfp/

<HOME>/                               ← the user's home folder, only that user
└── skills-conduct/
    └── space-<spaceId>/             personal skills, this user in this space only
        └── (created when that user saves a skill in this space)

Skill Precedence

Skills are applied in the following order, from base to top. When a skill name appears in more than one layer, the highest layer wins outright — its folder replaces the lower layer's skill wholesale, including scripts/, references/, and assets/. Nothing is merged.

1. Built-in skills — shipped with the product (see below)

2. Plain folders — any folder without a reserved prefix

3. company-* and space-*

4. team-*

5. Personal skills — only the current user's home folder for this space, <HOME>/skills-conduct/space-<spaceId>/, applied last

Within one layer, the root folder wins over an additional folder. If the same skill name exists in both, the agent uses the copy from the root.

Two things follow from this that are worth knowing before you name folders:

• The privacy boundary for personal skills is the user's home folder. Only that user can open it, and a session loads only the space-<spaceId> folder of the space it runs in. Personal skills a user saved in another space are never loaded.

• A personal-<userId> folder under a skills folder gets no boundary. It is loaded as a company folder for everyone in scope. Skills saved there before this change were not migrated: they are still available, they are not marked Personal in Settings, and access to them still follows the permissions on that folder. See Configuring Skills for a Space.

Promoting a Skill to a Wider Audience

A skill that proves useful for one person is often worth sharing with a team or the whole company. To promote a skill, copy the skill folder into the wider layer (team-* or company-*) and grant access accordingly.

Built-in Skills

Conduct ships a set of built-in skills bundled with the product. These are not stored in the Knowledge Base and require no configuration:

browser-portal-download, create-skill, doc-generator-shared, docx, edit-skill, interactive-html, pdf, pptx, skill-versions, template-selection, unique-cli-browser, user-memory, xlsx, …

Six of them appear only when the corresponding feature is enabled on the space:

Separately, each connected capability contributes its own unique-cli-* skill automatically — knowledge base search, web search, MCP connectors, sub-agents and others appear when their tool is enabled and disappear when it is turned off. If the agent lists a skill you don't recognize from the set above, this is usually why.

Company Templates

The pptx, docx, and pdf skills build documents from your organization's own templates. Those templates are kept in a fixed Knowledge Base folder and are not configured per space. Setting up and maintaining that folder is covered in Company Templates for Document Skills.

Overriding a Built-in Skill

Any built-in skill can be replaced without a deployment. Create a folder whose name matches the built-in skill name character-for-character, containing a SKILL.md, inside one of the precedence layers — for example company-core/docx/ to replace docx company-wide, or team-credit/pptx/ for one desk only. The Knowledge Base version then fully replaces the bundled skill.

Two caveats: put the override inside a layer folder, not a plain folder — a plain folder overlays files on top of the bundled skill rather than replacing it cleanly. And if the name does not match exactly, you get an additional skill rather than an override.

Company-Specific Skills

In addition to the built-in skills, we recommend organizations develop their own skills for their most common workflows. The agent can help — users can instruct Conduct to create skills directly in a session.

We recommend developing company-specific skills where:

• Intellectual property is involved (proprietary models, analysis frameworks)

• Secure system access is required (internal APIs, databases)

• House style needs enforcement (memo formats, branding, disclaimers)

• Regulatory compliance demands specific output structures

Configuring Skills for a Space

Everything in this section is on the space, in the admin app: open the Conduct space, open Tools, and open the Skills tool. The settings sit on the Sources card. The root folder and the additional folders are the shared skills this space can use. Each user also gets the personal skills they saved in this space. In a chat in this space, + then Skills lists those skills. Settings → Skills lists every skill the person can see, including skills this space does not load. A team or company skill in Settings is not available in this space until its folder is the root or an additional folder here.

Root folder

This is the folder the space treats as home for shared skills.

• New spaces default to skills-conduct. Pick another folder when this space should load a different set.

• Every skill under this folder is eligible: company skills and team skills.

• New personal skills are never written here. They go to the user's home folder.

Personal skills creation

The switch is labeled Personal skills creation. It is on by default. The meaning is: let users create and save their personal skills for this space, in their own home folder.

• On. A user can ask the agent to save a skill. The skill file lands in that user's home folder, under skills-conduct/space-<spaceId>. Only that user can open that folder. Other users' home folders are never loaded.

• Off. The agent will not persist a new skill, and it tells the user that skill creation is disabled for this space. Skills that user already saved for this space stay loaded and stay listed in Settings. The switch does not hide them and does not delete them.

Additional sources

Add additional folder from where skills are loaded. What you can attach, and what is left out:

Check what a user will see

1. Open the space as that user.

2. In a chat in this space, click +, then Skills. That list should match the root folder, the additional folders, and that user's personal skills for this space, and nothing else. Settings → Skills is the wider catalog and will include skills this space does not use. How users act on each list is in Skills in Unique AI Conduct.

3. Or ask the agent: “What skills do you have available?”

Writing Effective Skills

The Description Matters Most

The description field in SKILL.md front matter is the primary trigger for skill selection. The agent reads it to decide whether to use the skill. Make it specific:

Good: "Extracts key data points, tables, and metadata from financial documents (10-K, DDQ, side letters). Use when the user uploads a financial PDF or asks to parse/extract from a regulatory document."

Bad: "Processes documents"

Instruction Patterns

• Explain the why — Tell the agent why each instruction matters, not just what to do. This helps it make judgment calls on edge cases.

• Include examples — Show input/output pairs so the agent understands the expected format.

• Define output structure — Specify the exact template or format the output should follow.

• Handle errors — Describe what to do when data is missing, malformed, or ambiguous.

• Keep it focused — One skill per workflow. Don't bundle unrelated capabilities.

Bundled Scripts

For deterministic or repetitive tasks, include executable scripts in scripts/. The agent can run these directly instead of writing code from scratch — faster and more reliable.

Testing Skills

We recommend an iterative testing loop:

1. Configure the full set of tools, MCP servers, sub-agents, and skills the agent will need in production

2. Run representative tasks end-to-end in the UI — observe tool selection, skill triggering, and output quality

3. Provide the agent feedback based on where the agent hesitated, misrouted, or produced poor output

4. Instruct the agent to update the existing skill from its own learnings and your feedback

Skill descriptions and instructions are the highest-leverage thing to tune — they determine whether the right skill fires and how well it executes.

FAQs

Q: How many skills can a space have?
A: There's no hard limit, but all skills are loaded at the start of a turn. A very large number increases setup time and can dilute the agent's ability to select the right one. Focus on quality over quantity.

Q: Can different spaces use different skills?
A: Yes. Each space’s Skills tool has its own root folder, and its own list of additional folders. Several spaces can share one root folder. Additional folders let one space also load company and team skills that live somewhere else, without moving those files and without writing new skills there. Personal skills are always per space: a skill a user saves in one space is not loaded in another.

Q: How do I update a skill?
A: Edit the skill files in the Knowledge Base. Users pick up the new version on a subsequent message — no space reconfiguration needed. Skills are cached briefly for performance, so allow a few minutes before concluding an edit didn't take.

Q: Can users override or disable a skill?
A: Users cannot disable a skill, but they can override one. Saving a skill through create-skill or edit-skill writes it to that user's home folder for this space, <HOME>/skills-conduct/space-<spaceId>/ — the highest precedence layer — so a same-named skill supersedes the company, team, or built-in version for that user only, in that space. Editing a shared skill forks a private copy rather than changing it for everyone. Users can also steer the agent explicitly in conversation (e.g. "don't use a template — give me raw output").

Q: Does turning off Personal skills creation remove skills people already saved?
A: No. The switch only stops new personal skills from being saved in that space. Personal skills already stored in a user's home folder for that space stay loaded for that user.

Q: What happened to existing personal-<userId> folders?
A: They were not migrated. Skills in them are still available, but they are not marked Personal in Settings, and access to them still follows the permissions on that folder. To make one private again, ask the user to save it again from a chat in the space, then delete the old folder.

Q: What happens if two skills overlap?
A: It depends on whether the names collide. Skills with different names are selected by description: the agent picks whichever description best matches the task, so overlapping descriptions can make selection unpredictable — keep them distinct and specific. Skills with the same name never compete, because precedence resolves them before the agent sees them: only the highest layer's version is loaded.

Q: Can skills access the Knowledge Base or external APIs?
A: A skill is a package of instructions and files, which may include executable scripts. It has no special access of its own, but it can direct the agent to use the tools the space already has — searching the Knowledge Base, calling an MCP server, and so on — as part of its workflow.

Q: Does any of this change when the space is called via the API?
A: No. A Conduct space is reachable through the Unique API like any other space, and API calls inherit the space's configuration — the same skills, tools, and precedence rules apply. The API flow is asynchronous: post a message, then poll for the reply. See the Unique API reference for endpoint details.